© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 22196
    Prev
    Next
    INDEX
    Explanations

    thick and thin descriptors

    np_acts-logits-general · gemini-2.5-flash-lite

    thick and thin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    to
    0.52
    ین
    0.49
    很多
    0.48
    骧
    0.46
     pengg
    0.45
     Our
    0.45
     décès
    0.44
     kapan
    0.43
    퐫
    0.43
    té
    0.43
    POSITIVE LOGITS
     thicker
    1.50
    厚
    1.50
     thicknesses
    1.36
    厚的
    1.34
     thick
    1.31
     thickness
    1.31
     Thick
    1.31
    薄
    1.30
    thick
    1.30
    thickness
    1.29
    Activations Density 0.037%

    No Known Activations